Method and device for detecting fineness of pulverized coal based on constant-speed sampling

Abstract

The invention discloses a pulverized coal fineness detection method and device based on constant-speed sampling, and belongs to the technical field of powder detection, and the method comprises the following steps: obtaining a pulverized coal conveying scheme; pulverized coal sampler layout parameters of the pulverized coal conveying pipeline are collected, and initial sampling position distribution is obtained; the initial sampling position distribution is adjusted according to the pulverized coal sampling value threshold value; performing constant-speed sampling on the pulverized coal conveying pipeline according to the optimized sampling position distribution to obtain Q pulverized coal samples; respectively carrying out fineness detection on the Q pulverized coal samples according to the pulverized coal fineness detection channel; carrying out moisture determination on the Q pulverized coal samples according to a pulverized coal moisture determination instrument; and performing interference correction on the Q pulverized coal fineness detection coefficients according to the Q pulverized coal moisture determination results to obtain a pulverized coal fineness detection report. The technical problems of low pulverized coal fineness detection precision and poor real-time performance caused by unreasonable sampling position distribution and insufficient interference correction in the prior art are solved.

Description

Technical Field

[0001] The invention relates to the technical field of powder detection, and in particular to a method and device for detecting coal powder fineness based on isokinetic sampling. Background Art

[0002] With the continuous growth of global energy demand, coal, as an important basic energy source, has become the focus of attention of all countries for its efficient utilization and environmentally friendly combustion. In the process of coal combustion, the fineness of coal powder directly affects the combustion efficiency, pollutant emissions and the operating stability of equipment. Accurate coal powder fineness detection is of great significance for optimizing the combustion process, improving energy utilization and reducing environmental pollution.

[0003] At present, the detection of coal powder fineness mainly relies on traditional offline sampling and laboratory analysis methods, which have the disadvantages of long sampling cycle, low detection accuracy, and poor real-time performance. In addition, the existing online detection technology still has deficiencies in the optimization of sampling position distribution and correction of interference factors, making it difficult to fully reflect the true fineness distribution of coal powder in the transportation pipeline. These limitations not only affect the accuracy and reliability of coal powder fineness detection, but also restrict the optimization control of the coal combustion process. Therefore, there is an urgent need for a coal powder fineness detection method based on advanced sampling technology and intelligent correction mechanism to improve detection efficiency and accuracy and meet the needs of the modern coal industry for high-quality combustion control. Summary of the invention

[0004] The present application provides a coal powder fineness detection method and device based on isokinetic sampling, aiming to solve the problems of unreasonable sampling position distribution and insufficient interference correction in the prior art, thereby leading to the technical problems of low coal powder fineness detection accuracy and poor real-time performance.

[0005] In view of the above problems, the present application provides a method and device for detecting coal powder fineness based on isokinetic sampling.

[0006] In a first aspect, a method for detecting coal powder fineness based on isokinetic sampling is provided, the method comprising obtaining a coal powder conveying scheme of a coal powder conveying pipeline; collecting the layout parameters of the coal powder sampler of the coal powder conveying pipeline to obtain an initial sampling position distribution; based on the coal powder conveying scheme, adjusting the initial sampling position distribution according to a coal powder sampling value threshold to generate an optimized sampling position distribution; based on the coal powder conveying scheme, isokinetically sampling the coal powder conveying pipeline according to the optimized sampling position distribution to obtain Q coal powder samples, wherein Q is a positive integer greater than 1; according to a coal powder fineness detection channel, respectively performing fineness detection on the Q coal powder samples to obtain Q coal powder fineness detection coefficients; performing moisture measurement on the Q coal powder samples according to a coal powder moisture meter to obtain Q coal powder moisture measurement results; performing interference correction on the Q coal powder fineness detection coefficients according to the Q coal powder moisture measurement results to obtain a coal powder fineness detection report.

[0007] In a second aspect, a coal powder fineness detection device based on isokinetic sampling is provided, the device comprising a conveying scheme acquisition module, used to obtain a coal powder conveying scheme of a coal powder conveying pipeline; a position distribution acquisition module, used to collect the coal powder sampler layout parameters of the coal powder conveying pipeline, and obtain an initial sampling position distribution; a position distribution adjustment module, used to adjust the initial sampling position distribution according to a coal powder sampling value threshold based on the coal powder conveying scheme, and generate an optimized sampling position distribution; an isokinetic sampling module, used to adjust the initial sampling position distribution according to the optimized sampling position distribution based on the coal powder conveying scheme The coal powder conveying pipeline performs isokinetic sampling to obtain Q coal powder samples, wherein Q is a positive integer greater than 1; a fineness detection module is used to perform fineness detection on the Q coal powder samples according to the coal powder fineness detection channel, and obtain Q coal powder fineness detection coefficients; a sample moisture determination module is used to perform moisture determination on the Q coal powder samples according to a coal powder moisture determination instrument, and obtain Q coal powder moisture determination results; a test report acquisition module is used to perform interference correction on the Q coal powder fineness detection coefficients according to the Q coal powder moisture determination results, and obtain a coal powder fineness detection report.

[0008] In a third aspect, the present application provides an electronic device, comprising: a processor; a memory for storing instructions executable by the processor; wherein the processor is used to execute a coal powder fineness detection method based on isokinetic sampling provided in the present application.

[0009] In a fourth aspect, the present application provides a computer-readable storage medium storing a computer program, and the computer program is used to execute a coal powder fineness detection method based on isokinetic sampling provided in the present application.

[0010] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0011] The adoption of a technical solution based on isokinetic sampling and optimized sampling position distribution solves the problems of unreasonable sampling position distribution and insufficient interference correction in the prior art, which leads to low coal powder fineness detection accuracy and poor real-time performance, and achieves the technical effect of improving the accuracy and reliability of coal powder fineness detection, ensuring that the sample is highly representative, and effectively eliminating moisture interference. By optimizing the sampling position and introducing an interference correction mechanism, the accuracy of the fineness detection report is significantly improved, providing solid data support for the optimization control of the coal combustion process and the improvement of energy utilization efficiency, while reducing pollutant emissions.

[0012] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 A schematic flow chart of a method for detecting coal powder fineness based on isokinetic sampling is provided for an embodiment of the present application;

[0014] Figure 2 A schematic structural diagram of a coal powder fineness detection device based on isokinetic sampling is provided for an embodiment of the present application;

[0015] Figure 3 A schematic diagram of the structure of an electronic device provided in this application.

[0016] Explanation of the reference numerals: transport scheme acquisition module 11, position distribution acquisition module 12, position distribution adjustment module 13, constant speed sampling module 14, fineness detection module 15, sample moisture determination module 16, test report acquisition module 17, processor 21, memory 22, input device 23, output device 24. DETAILED DESCRIPTION

[0017] The overall idea of ​​the technical solution provided by this application is as follows:

[0018] The embodiment of the present application provides a method and device for detecting the fineness of coal powder based on isokinetic sampling. First, by analyzing the coal powder conveying scheme, the initial sampling position is adjusted and its distribution is optimized. Then, isokinetic sampling is performed based on the optimized sampling position, and the fineness of the sample is detected. Finally, the fineness detection coefficient is interfered with and corrected in combination with the moisture determination result, so as to obtain a high-precision coal powder fineness detection report.

[0019] After introducing the basic principles of the present application, various non-limiting implementation methods of the present application will be specifically described below in conjunction with the drawings in the specification.

[0020] Embodiment 1, as Figure 1 As shown, the embodiment of the present application provides a method for detecting coal powder fineness based on isokinetic sampling, the method comprising:

[0021] Step S100: obtaining a pulverized coal conveying plan for a pulverized coal conveying pipeline.

[0022] Specifically, the pulverized coal pipeline refers to a dedicated pipeline system used to transport pulverized coal, usually made of steel or wear-resistant materials to meet the transportation needs of pulverized coal under high temperature, high pressure and high-speed flow conditions. The pulverized coal transportation plan refers to the detailed transportation plan and operating parameters formulated for a specific pulverized coal transportation pipeline system, including the pulverized coal transportation method (such as pneumatic transportation, screw transportation, etc.), flow rate, pressure, temperature, pipeline layout, sampling point location, etc.

[0023] First, a comprehensive investigation and analysis of the conveying system is required. This includes collecting basic information about the pipeline, such as the length, diameter, material, number and location of elbows, etc. In addition, it is necessary to understand the specific process parameters of coal powder transportation, including coal powder particle size distribution, humidity, transportation distance, transportation speed, and the type of transportation equipment used (such as blowers, fans, etc.). On this basis, computational fluid dynamics software is used to simulate and analyze the flow behavior of coal powder in the pipeline.

[0024] By obtaining and optimizing the delivery scheme of the coal powder conveying pipeline, the stability and efficiency of the coal powder conveying process can be significantly improved, and energy consumption and equipment wear can be reduced. In addition, the optimized delivery scheme helps to accurately locate the sampling point, ensure the representativeness and accuracy of the subsequent coal powder fineness detection, and thus improve the reliability of the overall detection system.

[0025] Step S200: collecting the layout parameters of the pulverized coal samplers of the pulverized coal conveying pipeline to obtain the initial sampling position distribution.

[0026] Specifically, a coal powder sampler is a device used to periodically or continuously collect coal powder samples from a coal powder conveying pipeline. The design of the sampler must ensure that the sample is representative and avoid deviations introduced by the sampling process. Common types of samplers include rotary samplers, static samplers, and automatic samplers. The layout parameters refer to the specific installation and configuration parameters of the coal powder sampler in the conveying pipeline, including the position, number, spacing, installation angle, sampling frequency, etc. of the sampler. The initial sampling position distribution refers to the specific distribution of the coal powder sampler in the conveying pipeline determined according to the layout parameters. This distribution determines the location and number of samples collected, affecting the accuracy of subsequent fineness detection.

[0027] First, the overall layout and operating conditions of the pulverized coal pipeline are understood in detail. This includes the length, diameter, number and location of elbows and branches, and transportation methods (such as pneumatic or spiral transportation). Next, the layout parameters of the samplers are determined, including the installation location, spacing, and number of samplers. For example, in a pulverized coal pipeline with a length of 1,000 meters and a diameter of 300 mm, 5 samplers may be installed at different locations according to the flow rate and coal characteristics, with a spacing of about 200 meters to ensure that the flow conditions of the entire pipeline are covered.

[0028] Use professional pipeline layout design software (such as AutoCAD or special coal powder transportation simulation software) to design and optimize the layout parameters to ensure that the sampler can effectively collect samples at key locations (such as pipeline elbows, reducers, or areas with significant flow rate changes). In actual operation, tools such as laser rangefinders and 3D scanning equipment can be used to accurately measure and record the positions of key points in the pipeline to ensure the precise installation of the sampler.

[0029] By systematically collecting the sampler layout parameters of the pulverized coal conveying pipeline and obtaining the initial sampling position distribution, it is possible to ensure that the collected pulverized coal samples are highly representative and accurate. In addition, reasonable sampler layout can also reduce equipment wear and maintenance costs, extend the service life of the sampler, and improve the overall operating efficiency and economy of the pulverized coal conveying system.

[0030] Step S300: Based on the pulverized coal conveying scheme, the initial sampling position distribution is adjusted according to the pulverized coal sampling value threshold to generate an optimized sampling position distribution.

[0031] Specifically, the coal dust sampling value threshold is a standard value used to evaluate the importance and representativeness of the sampling location. If the sampling value coefficient is higher than the threshold, it means that the sampling at this location has a high representativeness and value; otherwise, the sampling location needs to be adjusted to improve the effectiveness of the overall sampling. Optimizing the sampling location distribution means adjusting the initial sampling location distribution so that the sampling value coefficient of each sampling point reaches or exceeds the sampling value threshold, thereby improving the representativeness of the overall sampling and the accuracy of detection.

[0032] First, a coal pulverized gas pipeline model needs to be constructed using the delivery plan and the initial sampling location distribution. This is usually simulated using computational fluid dynamics software to predict the flow and distribution of coal pulverized gas at different sampling locations.

[0033] For example, in the coal pulverized conveying system of a thermal power plant, the initial sampling position distribution includes two sampling points at the beginning, middle and end of the pipeline. However, the simulation results show that the sampling value coefficient of a sampling point in the middle section is lower than the set threshold, indicating that the sampling representativeness of this position is insufficient. At this time, engineers can re-evaluate the simulation by adjusting the position of the sampler, such as increasing the number of sampling points or redistributing the spacing between samplers. Using optimization algorithm tools (such as genetic algorithms or particle swarm optimization algorithms), the sampling position adjustment scheme space is iteratively searched to screen out the optimal sampling position distribution that can make the sampling value coefficients of most sampling points reach or exceed the threshold. Ultimately, the generated optimized sampling position distribution ensures that more sampling points are set up in key areas (such as pipeline elbows where flow velocity changes significantly or coal pulverized deposition is prone to occur) to improve the representativeness and effectiveness of the overall sampling.

[0034] By adjusting the initial sampling location distribution based on the sampling value threshold and generating an optimized sampling location distribution, the representativeness of the coal powder sample and the accuracy of the detection can be significantly improved. This optimization process ensures that the sampling point distribution is more reasonable, covering all key areas in the coal powder transportation process, and reducing data deviations caused by improper sampling locations.

[0035] Step S400: Based on the pulverized coal conveying scheme, the pulverized coal conveying pipeline is sampled at a constant speed according to the optimized sampling position distribution to obtain Q pulverized coal samples, where Q is a positive integer greater than 1.

[0036] Specifically, isokinetic sampling is a sampling method widely used in fluid dynamics, which aims to ensure that the sample flow rate is the same as the actual flow rate of the fluid in the pipeline. This can avoid sampling deviations caused by flow rate differences and ensure the representativeness and accuracy of the samples. In coal powder transportation, isokinetic sampling helps to obtain coal powder samples that are consistent with the actual transportation status. Q coal powder samples refer to multiple independent coal powder samples obtained by isokinetic sampling. Q is a positive integer greater than 1, which represents the number of samples, ensuring that the samples are diverse and representative to reflect the overall fineness distribution of coal powder in the transportation pipeline.

[0037] First, isokinetic samplers are installed at key locations in the conveying pipeline based on the optimized sampling location distribution. These samplers usually include rotary samplers or automated sampling devices that can collect coal powder samples while maintaining the same flow rate as in the pipeline. Next, a flow rate measuring instrument (such as a hot wire anemometer or Doppler anemometer) is used to monitor the coal powder flow rate in the pipeline in real time to ensure that the sampling speed of the sampler matches the actual flow rate during the sampling process. This process is usually achieved through an automatic control system to ensure the isokinetic nature of the sampling.

[0038] Under constant speed conditions, the samplers start to collect coal powder samples. Each sampler continuously or intermittently collects coal powder samples according to the set sampling frequency and time to ensure that the sample volume is sufficient and representative. Finally, the control system coordinates the work of each sampler to ensure that Q coal powder samples are collected at a constant speed at each sampling point during the entire sampling process. These samples are then sent to the fineness detection and moisture measurement equipment for subsequent analysis.

[0039] The isokinetic sampling method based on optimizing the sampling position distribution can significantly improve the representativeness of the coal powder sample and the accuracy of the detection. Isokinetic sampling ensures that the sample flow rate is consistent with the actual flow rate in the pipeline, avoiding sampling deviation caused by flow rate differences, so that the Q coal powder samples obtained can fully reflect the fineness distribution and flow state of the coal powder in the transportation pipeline.

[0040] Step S500: According to the coal powder fineness detection channel, the Q coal powder samples are respectively subjected to fineness detection to obtain Q coal powder fineness detection coefficients.

[0041] Specifically, the coal powder fineness detection channel refers to a system used to analyze and measure the particle size distribution of coal powder samples. This channel usually includes a particle size detection device and a fineness evaluation model, which aims to efficiently and accurately evaluate the fineness characteristics of coal powder. Fineness detection refers to the measurement and analysis of the particle size in the coal powder sample by specific methods and equipment to determine its fineness distribution. The fineness detection results are usually expressed as a particle size distribution curve or statistical parameters (such as average particle size, median particle size, etc.). The fineness detection coefficient is a numerical indicator that quantifies the fineness characteristics of the coal powder sample, and is used to indicate the specific situation of the coal powder particle size distribution. Each sample corresponds to a detection coefficient, and multiple coefficients jointly reflect the fineness of the overall coal powder.

[0042] First, prepare the fineness detection channel. The coal powder fineness detection channel usually consists of a particle size detection device (such as a laser particle size analyzer, an image recognition system) and a fineness evaluation model. Next, process Q coal powder samples one by one. Each sample is analyzed through the fineness detection channel. The specific steps include: evenly dispersing the coal powder samples to avoid aggregation and ensure the accuracy of the test results. Introducing the sample into the particle size detection device for particle size distribution measurement. Taking the laser particle size analyzer as an example, the sample is dispersed in the airflow, the laser beam passes through the sample, and the scattered light signal is captured by the sensor and converted into particle size distribution data. The fineness evaluation model analyzes the measured particle size distribution data and calculates the fineness detection coefficient. The model may include statistical analysis, machine learning algorithms, or empirical formulas to comprehensively evaluate the fineness characteristics of coal powder.

[0043] Through the coal powder fineness detection channel, Q coal powder samples are tested for fineness and Q fineness detection coefficients are obtained, which not only improves the accuracy and real-time performance of coal powder fineness detection, but also provides reliable data support for the optimization control of the coal combustion process. Through advanced detection equipment and intelligent evaluation models, the fineness distribution of coal powder is fully reflected, the overall performance of the system is improved, and it has broad application prospects and significant technical advantages.

[0044] Step S600: measuring the moisture content of the Q coal powder samples using a coal powder moisture meter to obtain Q coal powder moisture content measurement results.

[0045] Specifically, a coal powder moisture meter is a special device used to measure the moisture content in coal powder samples. Common moisture determination methods include loss on drying, Karl Fischer Titration, and near infrared spectroscopy (NIR). The instrument can quickly and accurately provide moisture content data of coal powder samples, and is an important tool for coal powder quality control and combustion optimization. The moisture determination result refers to the specific moisture content data obtained after measuring each coal powder sample through the coal powder moisture meter, usually expressed as a percentage (%). These results are used to evaluate the drying state and combustion performance of coal powder.

[0046] First, prepare the moisture meter. Select the appropriate type of coal powder moisture meter based on the measurement needs and accuracy requirements. Next, process Q coal powder samples one by one. For each coal powder sample (qth sample, 1≤q≤Q), prepare and measure the sample according to the instrument operating specifications. The moisture measurement results of each sample are automatically recorded by the instrument, and the data is processed and analyzed through the connected software. Ensure that all measurement results are accurate and stored in the database for subsequent use.

[0047] The moisture content of Q coal powder samples was measured by using a coal powder moisture meter to obtain Q moisture content results, which not only improved the accuracy and efficiency of coal powder moisture detection, but also provided reliable data support for subsequent interference correction and combustion optimization.

[0048] Step S700: performing interference correction on the Q coal powder fineness detection coefficients according to the Q coal powder moisture measurement results to obtain a coal powder fineness detection report.

[0049] Specifically, interference correction refers to the correction of the fineness detection coefficient according to the moisture content in the coal powder sample during the coal powder fineness detection process to eliminate the influence of moisture on the fineness measurement results. This process ensures that the fineness detection results are more accurate and reliable. The coal powder fineness detection report is a formal report generated based on the coal powder fineness detection results after interference correction. It records the fineness distribution and related analysis data of the coal powder sample in detail, providing a basis for combustion process optimization and quality control. The interference correction model is a model based on mathematical or machine learning algorithms, which is used to correct the fineness detection coefficient according to the moisture determination results, eliminate the interference of moisture on fineness measurement, and improve the accuracy of the detection results.

[0050] First, collect the moisture measurement results of Q coal powder samples. After completing the moisture measurement of each coal powder sample, obtain the corresponding moisture content data. Next, evaluate the interference effect. Since the moisture in the coal powder will affect the measurement results of the particle size detection device, it is necessary to evaluate the degree of interference on the fineness detection coefficient based on the moisture content. By establishing an interference correction model (such as a model based on a fully connected neural network), the moisture measurement results and initial fineness detection coefficient of each sample are input to predict and calculate the interference coefficient. The interference coefficient is applied to the initial fineness detection coefficient, corrected, and the corrected fineness detection coefficient is obtained. For example, the initial fineness detection coefficient of sample 1 of 0.75 is combined with the moisture content of 5.2% using a fully connected neural network model to output a corrected fineness detection coefficient of 0.77.

[0051] All corrected fineness test coefficients are summarized to generate a detailed coal fineness test report. The report includes the initial fineness test coefficient, moisture content, corrected fineness test coefficient and analysis results of each sample.

[0052] By performing interference correction on Q coal powder fineness detection coefficients according to Q coal powder moisture measurement results, a coal powder fineness detection report is obtained, which not only improves the accuracy and reliability of fineness detection, but also provides solid data support for the optimization control of the combustion process.

[0053] Furthermore, based on the coal powder conveying scheme, the initial sampling position distribution is adjusted according to the coal powder sampling value threshold to generate an optimized sampling position distribution, including: modeling according to the coal powder conveying pipeline to obtain a coal powder conveying pipeline model; based on the coal powder conveying scheme and the initial sampling position distribution, simulated sampling is performed according to the coal powder conveying pipeline model to obtain a coal powder simulation sampling result; sampling value is evaluated according to the coal powder simulation sampling result to obtain a coal powder sampling value coefficient; it is determined whether the coal powder sampling value coefficient is less than the coal powder sampling value threshold; if the coal powder sampling value coefficient is less than the coal powder sampling value threshold, the initial sampling position distribution is adjusted according to the coal powder sampling value threshold to obtain the optimized sampling position distribution.

[0054] Specifically, simulated sampling refers to the use of a coal pulverized pipeline model to simulate the actual sampling process in a virtual environment to predict the sampling effect and representativeness of different sampling locations. Sampling value assessment is to analyze the simulated sampling results to evaluate the representativeness and effectiveness of the samples collected at each sampling location. The sampling value coefficient is used to quantify the sampling value of each sampling point and determine whether it meets the preset sampling value threshold.

[0055] The flow behavior of pulverized coal in the pipeline is simulated using computational fluid dynamics software. Specifically, the basic parameters of the pulverized coal conveying pipeline are collected, including pipeline length, diameter, material, number and position of elbows, and conveying method (such as pneumatic conveying or screw conveying). At the same time, the physical properties of pulverized coal, such as particle size distribution, humidity, density, and conveying volume, are obtained. Next, a suitable computational fluid dynamics (CFD) software, such as ANSYS Fluent or CFX, is selected as a modeling tool. In the software, a three-dimensional pipeline model is constructed based on the collected pipeline geometric parameters and pulverized coal characteristics, and boundary conditions such as inlet flow rate, pressure, and temperature are set. Then, meshing is performed to ensure that key areas (such as elbows and diameter changes) have higher mesh density to improve simulation accuracy. After completing the model setting, a numerical simulation is run to analyze the flow behavior, pressure distribution, and possible blockage points of pulverized coal in the pipeline. In order to verify the accuracy of the model, the simulation results need to be compared with the actual operation data, and the model parameters need to be adjusted for calibration.

[0056] Next, based on the coal powder transportation scheme and the initial sampling position distribution, the constructed coal powder transportation pipeline model is used to simulate sampling to obtain the coal powder simulation sampling results. These results reflect the sampling effect of each sampling point in the actual transportation process. Subsequently, the sampling value is evaluated based on the simulated sampling results, and the sampling value coefficient of each sampling point is calculated. The sampling value coefficient is used to measure the representativeness of the samples collected at the sampling point in the overall coal powder distribution. If the sampling value coefficient of some sampling points is lower than the preset coal powder sampling value threshold, it means that the sampling of these sampling points is not representative enough and needs to be adjusted.

[0057] Finally, determine whether the sampling value coefficient is less than the coal dust sampling value threshold. If there are sampling points with a sampling value coefficient lower than the threshold, adjust the initial sampling position distribution according to the sampling value threshold, redistribute or increase the sampling points, and ensure that the sampling value coefficients of all sampling points reach or exceed the threshold. Through this process, an optimized sampling position distribution is generated to improve the representativeness of sampling and the accuracy of detection.

[0058] By adjusting the initial sampling position distribution based on the coal powder transportation scheme and the sampling value threshold, the optimized sampling position distribution is generated, which significantly improves the representativeness of sampling and the accuracy of fineness detection. The optimized sampling position distribution can fully cover the key areas in the coal powder transportation pipeline, ensuring that the collected coal powder samples can truly reflect the fineness distribution and flow characteristics of the entire transportation process. This not only reduces the data deviation caused by unreasonable sampling positions, but also improves the reliability and real-time performance of the fineness detection system.

[0059] Further, if the coal powder sampling value coefficient is less than the coal powder sampling value threshold, the initial sampling position distribution is adjusted according to the coal powder sampling value threshold to obtain the optimized sampling position distribution, including: if the coal powder sampling value coefficient is less than the coal powder sampling value threshold, the initial sampling position distribution is adjusted to establish a sampling position adjustment scheme space; according to the sampling position adjustment scheme space, a first sampling position adjustment scheme is extracted; based on the coal powder transportation scheme and the first sampling position adjustment scheme, a simulated sampling value evaluation is performed according to the coal powder transportation pipeline model to obtain a first adjustment scheme sampling value coefficient; it is determined whether the sampling value coefficient of the first adjustment scheme is greater than or equal to the coal powder sampling value threshold; if the sampling value coefficient of the first adjustment scheme is greater than or equal to the coal powder sampling value threshold, the first sampling position adjustment scheme is added to the optimized sampling position distribution; if the sampling value coefficient of the first adjustment scheme is less than the coal powder sampling value threshold, the first sampling position adjustment scheme is eliminated, and the sampling position adjustment scheme space is continued to be iteratively optimized according to the coal powder sampling value threshold until the optimized sampling position distribution is generated.

[0060] Specifically, the sampling position adjustment scheme space refers to the set of all possible sampling position adjustment schemes. Each scheme includes a different sampler position distribution to optimize the representativeness and effectiveness of the overall sampling. Iterative optimization refers to the continuous optimization of the sampler layout by repeatedly adjusting and evaluating the sampling position scheme until the sampling value coefficients of all sampling points meet or exceed the threshold.

[0061] Based on the above method, when it is detected that the coal dust sampling value coefficient of some sampling points is lower than the preset coal dust sampling value threshold, the initial sampling position distribution needs to be adjusted to generate an optimized sampling position distribution. Specifically, a sampling position adjustment scheme space is established. This step involves defining all possible sampling position adjustment schemes, including the addition, deletion or repositioning of samplers. Multiple adjustment schemes can be generated using design software (such as MATLAB or dedicated optimization software).

[0062] Next, extract the first sampling position adjustment scheme. Select a specific adjustment scheme from the adjustment scheme space, for example, move one of the two sampling points in the middle section to the elbow to improve the sampling value of this area. Then, based on the pulverized coal transportation scheme and the first adjustment scheme, use the pulverized coal transportation pipeline model to simulate the sampling value assessment. Use CFD software (such as ANSYS Fluent) to simulate the adjusted sampling position and calculate the sampling value coefficient of each sampling point.

[0063] Determine whether the sampling value coefficient of the first adjustment scheme reaches the threshold. If the sampling value coefficients of all sampling points in the scheme are greater than or equal to the preset threshold, the adjustment scheme is included in the optimized sampling position distribution. If the sampling value coefficient of the first adjustment scheme is still lower than the threshold, it is necessary to eliminate the scheme and continue iterative optimization. This means excluding the schemes that do not meet the requirements from the sampling position adjustment scheme space and selecting the next adjustment scheme for evaluation. Repeat this process until one or more optimized sampling position distributions are found that meet the requirements that the sampling value coefficients of all sampling points reach or exceed the threshold.

[0064] By adjusting the initial sampling position distribution based on the coal powder sampling value threshold, an optimized sampling position distribution is generated, which significantly improves the representativeness of sampling and the accuracy of fineness detection. The optimized sampling position distribution can more comprehensively cover key areas in the coal powder conveying pipeline, such as elbows where the flow rate changes significantly or where deposition is prone to occur, ensuring that the collected samples can truly reflect the overall fineness distribution and flow characteristics of the coal powder. This not only reduces the data deviation caused by unreasonable sampling positions, but also improves the reliability and real-time performance of the fineness detection system.

[0065] Furthermore, according to the coal powder fineness detection channel, the Q coal powder samples are respectively subjected to fineness detection to obtain Q coal powder fineness detection coefficients, including: the coal powder fineness detection channel includes a coal powder particle size detection branch and a coal powder fineness evaluation branch, wherein the coal powder particle size detection branch includes a coal powder particle size detection device, and the coal powder fineness evaluation branch includes P coal powder fineness evaluation models, where P is a positive integer greater than 1; according to the Q coal powder samples, the qth coal powder sample is extracted, wherein q is a positive integer, 1≤q≤Q; according to the coal powder particle size detection branch, the particle size of the qth coal powder sample is detected to obtain the qth coal powder particle size detection result; the qth coal powder particle size detection result is input into the coal powder fineness evaluation branch to generate the qth coal powder fineness detection coefficient, and the qth coal powder fineness detection coefficient is added to the Q coal powder fineness detection coefficients.

[0066] Specifically, the coal powder particle size detection branch is a component in the coal powder fineness detection channel, which is responsible for the specific measurement of the particle size of the coal powder sample. This branch usually contains a high-precision particle size detection device, such as a laser particle size analyzer, which is used to obtain the particle size distribution data of the sample. The coal powder fineness evaluation branch is another component in the coal powder fineness detection channel, which is responsible for further analysis and evaluation of the particle size detection results. This branch usually contains multiple fineness evaluation models, which are used to comprehensively analyze the particle size data and generate fineness detection coefficients. The coal powder fineness evaluation model is a mathematical or algorithmic model used to process and analyze particle size detection data. P coal powder fineness evaluation models refer to multiple independent evaluation models, which usually use different algorithms or parameters to improve the accuracy and reliability of the evaluation results, where P is a positive integer greater than 1, indicating the number of evaluation models.

[0067] First, prepare the coal powder fineness detection channel. This channel includes two main branches: coal powder particle size detection branch and coal powder fineness evaluation branch. In the particle size detection branch, a high-precision particle size detection device is installed to measure the particle size of coal powder samples. In the fineness evaluation branch, P fineness evaluation models are configured. Specifically, a large number of particle size distribution data and corresponding fineness detection results of coal powder samples collected under different conditions are collected. Subsequently, the data preprocessing step cleans, normalizes and extracts features to ensure the effectiveness of model training. Next, select appropriate model algorithms, such as linear regression, support vector machine (SVM), neural network, etc., and use tools such as MATLAB, Python (using Scikit-learn or TensorFlow) to design and train the model. Through training and verification, use part of the data to train the model, and the other part of the data for verification, and adjust the model parameters to optimize the performance. Finally, the model is evaluated and optimized, and cross-validation, error analysis and other methods are used to ensure that the model has good generalization ability and high precision.

[0068] Next, Q coal powder samples are processed one by one. For each coal powder sample (the qth sample, 1≤q≤Q), the particle size detection is first performed through the coal powder particle size detection branch to obtain the particle size detection result of the sample. Subsequently, the particle size detection result of the qth coal powder sample is input into the P fineness evaluation models in the coal powder fineness evaluation branch. Each evaluation model independently processes the particle size data and generates a corresponding fineness detection coefficient. By combining the evaluation results of the P models, the qth coal powder fineness detection coefficient is generated.

[0069] Through the coal powder fineness detection channel, Q coal powder samples are tested for fineness and Q fineness detection coefficients are obtained, which not only improves the accuracy and real-time performance of coal powder fineness detection, but also provides reliable data support for the optimization control of coal combustion process. This method comprehensively reflects the fineness distribution of coal powder through multi-model evaluation and systematic detection process, and improves the overall performance and economic benefits of the detection system.

[0070] Furthermore, the qth coal powder particle size detection result is input into the coal powder fineness evaluation branch to generate the qth coal powder fineness detection coefficient, including: inputting the qth coal powder particle size detection result into the P coal powder fineness evaluation models to obtain P coal powder fineness evaluation coefficients; performing sum calculations on the P coal powder fineness evaluation accuracies corresponding to the P coal powder fineness evaluation models to obtain the sum of the fineness evaluation accuracies; performing ratio calculations on the sum of the fineness evaluation accuracies according to the P coal powder fineness evaluation accuracies to obtain P fineness evaluation incentive coefficients; performing weighted calculations on the P coal powder fineness evaluation coefficients according to the P fineness evaluation incentive coefficients to obtain the qth coal powder fineness detection coefficient.

[0071] Specifically, the fineness assessment accuracy indicates the accuracy and reliability of each coal powder fineness assessment model in fineness detection. The sum of fineness assessment accuracy refers to the sum of the fineness assessment accuracy of all P assessment models, and the sum value obtained is used for the subsequent calculation of the incentive coefficient. According to the fineness assessment accuracy of each assessment model, the ratio of the sum of the fineness assessment accuracy is calculated to obtain the incentive coefficient of each model. The incentive coefficient is used to weightedly calculate the final fineness detection coefficient to ensure that the high-precision model contributes more to the final result. The qth coal powder sample refers to the qth specific coal powder sample among the Q coal powder samples, where q is a positive integer, 1≤q≤Q.

[0072] First, the qth coal powder particle size test result is input into P coal powder fineness evaluation models. Assuming P = 3, three different fineness evaluation models (such as linear regression model, support vector machine model and neural network model) are used to analyze the particle size test results respectively to obtain three independent fineness evaluation coefficients. For example, sample q is 0.75 through the linear regression model, 0.78 through the support vector machine model, and 0.80 through the neural network model.

[0073] Next, the fineness evaluation accuracies corresponding to the P models are summed up to obtain the sum of the fineness evaluation accuracies. Assuming that the evaluation accuracy of the linear regression model is 0.85, the support vector machine model is 0.90, and the neural network model is 0.95, the sum of the fineness evaluation accuracies is 0.85+0.90+0.95=2.70.

[0074] Then, according to the fineness assessment accuracy of P models, the sum of the fineness assessment accuracy is calculated by ratio, and P fineness assessment incentive coefficients are obtained. The specific calculation method is to divide the assessment accuracy of each model by the sum. Finally, according to the P fineness assessment incentive coefficients, the P fineness assessment coefficients are weighted and calculated to obtain the qth coal powder fineness detection coefficient.

[0075] By inputting the qth coal powder particle size detection result into P fineness evaluation models and performing weighted calculation based on the evaluation accuracy of each model, the qth coal powder fineness detection coefficient is generated, which can significantly improve the accuracy and reliability of fineness detection. The multi-model evaluation method combines the advantages of different algorithms, reduces the errors that may be caused by a single model, and ensures that the fineness detection coefficient more comprehensively reflects the true fineness characteristics of the coal powder sample.

[0076] Furthermore, interference correction is performed on the Q coal powder fineness detection coefficients according to the Q coal powder moisture measurement results to obtain a coal powder fineness detection report, including: extracting the qth coal powder moisture measurement result according to the Q coal powder moisture measurement results; performing detection interference evaluation on the qth coal powder fineness detection coefficient according to the qth coal powder moisture measurement result to obtain the qth coal powder detection interference coefficient; judging whether the qth coal powder detection interference coefficient is greater than or equal to the coal powder detection interference threshold; if the qth coal powder detection interference coefficient is greater than or equal to the coal powder detection interference threshold, performing interference correction on the qth coal powder fineness detection coefficient according to the qth coal powder moisture measurement result to obtain the qth corrected fineness detection coefficient; and adding the qth corrected fineness detection coefficient to the coal powder fineness detection report.

[0077] Specifically, the qth coal powder moisture determination result refers to the specific moisture content data obtained for the qth sample (1≤q≤Q) among Q coal powder samples. Detection interference evaluation refers to evaluating the influence of moisture on the fineness detection coefficient based on the coal powder moisture determination result, and calculating the interference coefficient to quantify the degree of interference. The coal powder detection interference threshold refers to the preset interference evaluation standard value, which is used to determine whether the interference coefficient of a certain sample has reached the level that requires correction. The qth corrected fineness detection coefficient refers to the corrected fineness detection coefficient of the qth coal powder sample obtained after interference correction, which reflects the true coal powder fineness characteristics.

[0078] First, extract the qth coal powder moisture measurement result. From the Q moisture measurement results, extract the corresponding moisture content data for each coal powder sample (qth sample). Next, perform detection interference evaluation on the qth coal powder fineness detection coefficient. Using an interference evaluation model (such as a model based on a fully connected neural network), input the moisture measurement result of the qth coal powder sample into the model to calculate the detection interference coefficient of the sample.

[0079] Subsequently, determine whether the qth coal powder detection interference coefficient is greater than or equal to the coal powder detection interference threshold. Assuming that the interference threshold is set to 0.80, if the interference coefficient of sample 1 is 0.85 ≥ 0.80, it is necessary to perform interference correction on its fineness detection coefficient. If the detection interference coefficient is greater than or equal to the threshold, the qth coal powder fineness detection coefficient is interference-corrected according to the qth coal powder moisture determination result. Using an interference correction model (such as a trained fully connected neural network), the moisture determination result and the initial fineness detection coefficient of the qth sample are input into the model, and the corrected fineness detection coefficient is output. Finally, the qth corrected fineness detection coefficient is added to the coal powder fineness detection report. Repeat the above steps to process all Q coal powder samples, and finally generate a complete detection report containing the corrected fineness detection coefficient.

[0080] By performing interference correction on Q coal powder fineness detection coefficients according to Q coal powder moisture measurement results, a coal powder fineness detection report is obtained, which not only improves the accuracy and reliability of fineness detection, but also provides solid data support for the optimization control of the combustion process.

[0081] Furthermore, if the qth coal powder detection interference coefficient is greater than or equal to the coal powder detection interference threshold, the qth coal powder fineness detection coefficient is interference corrected according to the qth coal powder moisture measurement result to obtain the qth corrected fineness detection coefficient, including: taking the coal powder moisture measurement sample set and the coal powder fineness detection sample set as input information, and taking the coal powder fineness correction sample set as output information, training the fully connected neural network to obtain the fineness detection interference correction accuracy; if the fineness detection interference correction accuracy is greater than or equal to the predetermined fineness detection interference correction accuracy, generating a coal powder fineness detection interference correction model; if the qth coal powder detection interference coefficient is greater than or equal to the coal powder detection interference threshold, activating the coal powder fineness detection interference correction model; inputting the qth coal powder moisture measurement result and the qth coal powder fineness detection coefficient into the coal powder fineness detection interference correction model, and outputting the qth corrected fineness detection coefficient.

[0082] Specifically, the sample set of coal powder moisture determination refers to a set of moisture determination data containing multiple coal powder samples collected during the training process of the interference correction model. These sample data are used to reflect the impact of different moisture contents on coal powder fineness detection. The sample set of coal powder fineness detection refers to a set of fineness detection data containing multiple coal powder samples, each sample corresponding to an initial fineness detection coefficient. These data are used to train the interference correction model to understand the specific interference of moisture on fineness detection. The sample set of coal powder fineness correction refers to the set of corrected fineness detection coefficients obtained after combining the moisture determination results and the initial fineness detection coefficients during the model training process. This sample set is used to guide the model to learn how to adjust the fineness detection results according to moisture. A fully connected neural network is an artificial neural network structure in which each neuron in each layer is connected to all neurons in the previous layer. FCNN is suitable for complex nonlinear relationship modeling, and is used in this method to learn the relationship between moisture and fineness detection coefficients. Fineness detection interference correction accuracy refers to the accuracy of the trained interference correction model in correcting the fineness detection coefficient. The predetermined fineness detection interference correction accuracy is the minimum accuracy standard set during the model training and evaluation phases to ensure that the interference correction model can reliably correct the fineness detection coefficient in practical applications.

[0083] First, an interference assessment model is constructed. The coal powder moisture determination sample set and coal powder fineness detection sample set are used as input and output data to train a fully connected neural network (FCNN). For example, using the TensorFlow or PyTorch platform, the input includes the moisture content of the sample and the initial fineness detection coefficient, and the output is the corrected fineness detection coefficient. Through training, the model learns the specific interference pattern of moisture on fineness detection and improves the correction accuracy.

[0084] Next, evaluate the interference correction accuracy. After the model training is completed, use the validation set data to evaluate the interference correction accuracy of the model to ensure that it meets or exceeds the predetermined accuracy standard. For example, if the predetermined accuracy is 95%, if the correction accuracy of the model on the validation set reaches 96%, the model training is considered successful.

[0085] Then, an interference correction model is generated. When the interference correction accuracy of the model reaches the predetermined standard, it is saved and deployed as part of the coal powder fineness detection system. This model is used to correct the detection results in real time. In actual applications, the interference correction model is activated. When the interference coefficient of a coal powder sample is detected to be greater than or equal to the threshold, the system automatically calls the interference correction model. The moisture measurement result and the initial fineness detection coefficient of the sample are input into the model, and the model outputs the corrected fineness detection coefficient. Finally, a coal powder fineness detection report is generated. All corrected fineness detection coefficients are summarized and a detailed report is generated for combustion optimization and quality control.

[0086] According to the Q coal powder moisture measurement results, Q coal powder fineness detection coefficients are interfered with and corrected to obtain a coal powder fineness detection report, which not only improves the accuracy and reliability of fineness detection, but also provides solid data support for the optimization control of the combustion process, ensuring the comprehensiveness and accuracy of the fineness detection results.

[0087] In summary, the coal powder fineness detection method based on isokinetic sampling provided in the embodiment of the present application has the following technical effects:

[0088] 1. By integrating and optimizing the sampling position distribution and interference correction steps, high accuracy and high reliability of coal powder fineness detection are achieved. This method ensures that the collected coal powder samples are representative and eliminates the influence of interference factors such as moisture on fineness detection, thereby providing accurate fineness detection reports and supporting the optimization control of the coal combustion process and the improvement of energy utilization efficiency.

[0089] 2. By building a coal powder transportation pipeline model and performing simulated sampling, the initial sampling location distribution can be dynamically evaluated and optimized. This step ensures the rationality and representativeness of the sampling location, improves the effectiveness of sampling, reduces data deviations caused by improper sampling locations, and further enhances the accuracy of fineness detection results and the overall performance of the system.

[0090] 3. Through the dual-branch structure of the fineness detection channel (particle size detection branch and fineness evaluation branch), a comprehensive analysis of the fineness of the coal powder sample is achieved. The multi-model evaluation mechanism improves the accuracy and consistency of fineness detection, reduces the error that may be caused by a single model, ensures the reliability and accuracy of the fineness detection results, and improves the overall performance of the detection system.

[0091] 4. By introducing the moisture determination and interference correction steps, the interference of moisture on the coal powder fineness detection is effectively eliminated. This method improves the accuracy and reliability of the fineness test results, ensures that the test report can truly reflect the fineness characteristics of the coal powder, and supports accurate combustion process optimization.

[0092] Embodiment 2 is based on the same inventive concept as the coal powder fineness detection method based on isokinetic sampling in the above embodiment. Figure 2 As shown, the embodiment of the present application provides a coal powder fineness detection device based on isokinetic sampling, the device comprising:

[0093] The conveying scheme acquisition module 11 is used to obtain the coal powder conveying scheme of the coal powder conveying pipeline; the position distribution acquisition module 12 is used to collect the coal powder sampler layout parameters of the coal powder conveying pipeline to obtain the initial sampling position distribution; the position distribution adjustment module 13 is used to adjust the initial sampling position distribution according to the coal powder sampling value threshold based on the coal powder conveying scheme to generate an optimized sampling position distribution; the isokinetic sampling module 14 is used to perform isokinetic sampling on the coal powder conveying pipeline according to the optimized sampling position distribution based on the coal powder conveying scheme , obtaining Q coal powder samples, wherein Q is a positive integer greater than 1; a fineness detection module 15, for performing fineness detection on the Q coal powder samples according to the coal powder fineness detection channel, and obtaining Q coal powder fineness detection coefficients; a sample moisture determination module 16, for performing moisture determination on the Q coal powder samples according to a coal powder moisture determination instrument, and obtaining Q coal powder moisture determination results; a test report obtaining module 17, for performing interference correction on the Q coal powder fineness detection coefficients according to the Q coal powder moisture determination results, and obtaining a coal powder fineness detection report.

[0094] Furthermore, the position distribution adjustment module 13 is also used to perform the following steps: modeling according to the coal powder conveying pipeline to obtain a coal powder conveying pipeline model; based on the coal powder conveying scheme and the initial sampling position distribution, simulated sampling is performed according to the coal powder conveying pipeline model to obtain a coal powder simulation sampling result; sampling value evaluation is performed according to the coal powder simulation sampling result to obtain a coal powder sampling value coefficient; it is determined whether the coal powder sampling value coefficient is less than the coal powder sampling value threshold; if the coal powder sampling value coefficient is less than the coal powder sampling value threshold, the initial sampling position distribution is adjusted according to the coal powder sampling value threshold to obtain the optimized sampling position distribution.

[0095] Furthermore, the position distribution adjustment module 13 is also used to perform the following steps: if the coal powder sampling value coefficient is less than the coal powder sampling value threshold, adjust the initial sampling position distribution and establish a sampling position adjustment scheme space; extract the first sampling position adjustment scheme according to the sampling position adjustment scheme space; based on the coal powder conveying scheme and the first sampling position adjustment scheme, perform a simulated sampling value evaluation according to the coal powder conveying pipeline model to obtain the sampling value coefficient of the first adjustment scheme; determine whether the sampling value coefficient of the first adjustment scheme is greater than or equal to the coal powder sampling value threshold; if the sampling value coefficient of the first adjustment scheme is greater than or equal to the coal powder sampling value threshold, add the first sampling position adjustment scheme to the optimized sampling position distribution; if the sampling value coefficient of the first adjustment scheme is less than the coal powder sampling value threshold, eliminate the first sampling position adjustment scheme, and continue to iterate and optimize the sampling position adjustment scheme space according to the coal powder sampling value threshold until the optimized sampling position distribution is generated.

[0096] Furthermore, the fineness detection module 15 is also used to perform the following steps: the coal powder fineness detection channel includes a coal powder particle size detection branch and a coal powder fineness evaluation branch, wherein the coal powder particle size detection branch includes a coal powder particle size detection device, and the coal powder fineness evaluation branch includes P coal powder fineness evaluation models, where P is a positive integer greater than 1; based on the Q coal powder samples, extract the qth coal powder sample, wherein q is a positive integer, 1≤q≤Q; perform particle size detection on the qth coal powder sample according to the coal powder particle size detection branch to obtain the qth coal powder particle size detection result; input the qth coal powder particle size detection result into the coal powder fineness evaluation branch to generate the qth coal powder fineness detection coefficient, and add the qth coal powder fineness detection coefficient to the Q coal powder fineness detection coefficients.

[0097] Furthermore, the fineness detection module 15 is also used to perform the following steps: input the qth coal powder particle size detection result into the P coal powder fineness assessment models to obtain P coal powder fineness assessment coefficients; perform sum calculations on the P coal powder fineness assessment accuracies corresponding to the P coal powder fineness assessment models to obtain the sum of the fineness assessment accuracies; perform ratio calculations on the sum of the fineness assessment accuracies according to the P coal powder fineness assessment accuracies to obtain P fineness assessment incentive coefficients; perform weighted calculations on the P coal powder fineness assessment coefficients according to the P fineness assessment incentive coefficients to obtain the qth coal powder fineness detection coefficient.

[0098] Furthermore, the detection report acquisition module 17 is also used to perform the following steps: extract the qth coal powder moisture measurement result based on the Q coal powder moisture measurement results; perform detection interference evaluation on the qth coal powder fineness detection coefficient based on the qth coal powder moisture measurement result to obtain the qth coal powder detection interference coefficient; determine whether the qth coal powder detection interference coefficient is greater than or equal to the coal powder detection interference threshold; if the qth coal powder detection interference coefficient is greater than or equal to the coal powder detection interference threshold, perform interference correction on the qth coal powder fineness detection coefficient based on the qth coal powder moisture measurement result to obtain the qth corrected fineness detection coefficient; and add the qth corrected fineness detection coefficient to the coal powder fineness detection report.

[0099] Furthermore, the detection report acquisition module 17 is also used to perform the following steps: using the coal powder moisture determination sample set and the coal powder fineness detection sample set as input information, and the coal powder fineness correction sample set as output information, training the fully connected neural network to obtain the fineness detection interference correction accuracy; if the fineness detection interference correction accuracy is greater than or equal to the predetermined fineness detection interference correction accuracy, generating a coal powder fineness detection interference correction model; if the qth coal powder detection interference coefficient is greater than or equal to the coal powder detection interference threshold, activating the coal powder fineness detection interference correction model; inputting the qth coal powder moisture determination result and the qth coal powder fineness detection coefficient into the coal powder fineness detection interference correction model, and outputting the qth corrected fineness detection coefficient.

[0100] Embodiment 3, Figure 3 The schematic diagram of the structure of the electronic device provided in the third embodiment of the present invention shows a block diagram of an exemplary electronic device suitable for implementing the implementation mode of the present invention. Figure 3 The electronic device shown is only an example and should not limit the functions and scope of use of the embodiments of the present invention. Figure 3 As shown, the electronic device includes a processor 21, a memory 22, an input device 23 and an output device 24; the number of processors 21 in the electronic device can be one or more. Figure 3 Taking a processor 21 as an example, the processor 21, memory 22, input device 23 and output device 24 in the electronic device can be connected through a bus or other means. Figure 3 The example of connecting through bus is taken in the following.

[0101] In the fourth embodiment, the memory 22 is a computer-readable storage medium that can be used to store software programs, computer executable programs and modules, such as program instructions / modules corresponding to a method for detecting coal fineness based on constant speed sampling in the embodiment of the present application. The processor 21 executes various functional applications and data processing of the computer device by running the software programs, instructions and modules stored in the memory 22, that is, realizing the above-mentioned method for detecting coal fineness based on constant speed sampling.

[0102] Any step of the method described above can be stored as a computer instruction or program in an unlimited computer memory, and can be called and recognized by an unlimited computer processor to implement any method in the embodiments of the present application, without any unnecessary restrictions.

[0103] Furthermore, the first or second mentioned above may not only represent an order relationship, but may also represent a specific concept, and / or refer to multiple elements that can be selected individually or in full. Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A method for detecting coal powder fineness based on isokinetic sampling, characterized in that: The method comprises: Obtain a pulverized coal transportation plan for the pulverized coal transportation pipeline; Collecting the layout parameters of the pulverized coal sampler of the pulverized coal conveying pipeline to obtain the initial sampling position distribution; Based on the pulverized coal conveying scheme, the initial sampling position distribution is adjusted according to the pulverized coal sampling value threshold to generate an optimized sampling position distribution; Based on the pulverized coal conveying scheme, the pulverized coal conveying pipeline is sampled at a constant speed according to the optimized sampling position distribution to obtain Q pulverized coal samples, where Q is a positive integer greater than 1; According to the coal powder fineness detection channel, the Q coal powder samples are respectively tested for fineness to obtain Q coal powder fineness detection coefficients; Measuring the moisture content of the Q coal powder samples using a coal powder moisture meter to obtain Q coal powder moisture content measurement results; The Q coal powder fineness detection coefficients are subjected to interference correction according to the Q coal powder moisture measurement results to obtain a coal powder fineness detection report.

2. The method according to claim 1, characterized in that Based on the pulverized coal conveying scheme, the initial sampling position distribution is adjusted according to the pulverized coal sampling value threshold to generate an optimized sampling position distribution, including: Modeling the pulverized coal conveying pipeline to obtain a pulverized coal conveying pipeline model; Based on the pulverized coal transportation scheme and the initial sampling position distribution, simulated sampling is performed according to the pulverized coal transportation pipeline model to obtain pulverized coal simulated sampling results; Perform sampling value assessment based on the coal powder simulation sampling results to obtain a coal powder sampling value coefficient; Determining whether the coal powder sampling value coefficient is less than the coal powder sampling value threshold; If the coal powder sampling value coefficient is less than the coal powder sampling value threshold, the initial sampling position distribution is adjusted according to the coal powder sampling value threshold to obtain the optimized sampling position distribution.

3. The method according to claim 2, characterized in that If the coal dust sampling value coefficient is less than the coal dust sampling value threshold, adjusting the initial sampling position distribution according to the coal dust sampling value threshold to obtain the optimized sampling position distribution, including: If the coal dust sampling value coefficient is less than the coal dust sampling value threshold, adjusting the initial sampling position distribution and establishing a sampling position adjustment plan space; Extracting a first sampling position adjustment scheme according to the sampling position adjustment scheme space; Based on the pulverized coal transportation scheme and the first sampling position adjustment scheme, a simulated sampling value assessment is performed according to the pulverized coal transportation pipeline model to obtain a sampling value coefficient of the first adjustment scheme; Determining whether the sampling value coefficient of the first adjustment scheme is greater than or equal to the coal powder sampling value threshold; If the sampling value coefficient of the first adjustment scheme is greater than or equal to the coal powder sampling value threshold, adding the first sampling position adjustment scheme to the optimized sampling position distribution; If the sampling value coefficient of the first adjustment scheme is less than the coal powder sampling value threshold, the first sampling position adjustment scheme is eliminated, and the sampling position adjustment scheme space is iteratively optimized according to the coal powder sampling value threshold until the optimized sampling position distribution is generated.

4. The method according to claim 1, characterized in that According to the coal powder fineness detection channel, the Q coal powder samples are respectively tested for fineness to obtain Q coal powder fineness detection coefficients, including: The coal powder fineness detection channel includes a coal powder particle size detection branch and a coal powder fineness evaluation branch, wherein the coal powder particle size detection branch includes a coal powder particle size detection device, and the coal powder fineness evaluation branch includes P coal powder fineness evaluation models, where P is a positive integer greater than 1; Extracting the qth coal powder sample according to the Q coal powder samples, wherein q is a positive integer, 1≤q≤Q; Performing a particle size test on the qth coal powder sample according to the coal powder particle size test branch to obtain a qth coal powder particle size test result; The qth coal powder particle size detection result is input into the coal powder fineness evaluation branch to generate the qth coal powder fineness detection coefficient, and the qth coal powder fineness detection coefficient is added to the Q coal powder fineness detection coefficients.

5. The method according to claim 4, characterized in that Inputting the qth coal powder particle size detection result into the coal powder fineness evaluation branch to generate the qth coal powder fineness detection coefficient includes: Inputting the qth coal powder particle size detection result into the P coal powder fineness evaluation models to obtain P coal powder fineness evaluation coefficients; Performing a summation calculation based on the P coal powder fineness assessment accuracies corresponding to the P coal powder fineness assessment models to obtain a sum of fineness assessment accuracies; According to the P coal powder fineness assessment accuracies, respectively performing ratio calculations on the sum of the fineness assessment accuracies to obtain P fineness assessment incentive coefficients; The P coal powder fineness assessment coefficients are weightedly calculated according to the P fineness assessment incentive coefficients to obtain the qth coal powder fineness detection coefficient.

6. The method according to claim 1, characterized in that According to the Q coal powder moisture measurement results, the Q coal powder fineness detection coefficients are subjected to interference correction to obtain a coal powder fineness detection report, including: Extracting the qth coal powder moisture measurement result according to the Q coal powder moisture measurement results; Performing a detection interference evaluation on the qth coal powder fineness detection coefficient according to the qth coal powder moisture measurement result to obtain the qth coal powder detection interference coefficient; determining whether the qth coal powder detection interference coefficient is greater than or equal to a coal powder detection interference threshold; If the qth coal powder detection interference coefficient is greater than or equal to the coal powder detection interference threshold, interference correction is performed on the qth coal powder fineness detection coefficient according to the qth coal powder moisture measurement result to obtain the qth corrected fineness detection coefficient; The qth correction fineness detection coefficient is added to the coal powder fineness detection report.

7. The method according to claim 6, characterized in that If the qth coal powder detection interference coefficient is greater than or equal to the coal powder detection interference threshold, interference correction is performed on the qth coal powder fineness detection coefficient according to the qth coal powder moisture measurement result to obtain the qth corrected fineness detection coefficient, including: With the coal powder moisture determination sample set and coal powder fineness detection sample set as input information and the coal powder fineness correction sample set as output information, the fully connected neural network is trained to obtain the fineness detection interference correction accuracy. If the fineness detection interference correction accuracy is greater than or equal to a predetermined fineness detection interference correction accuracy, generating a coal powder fineness detection interference correction model; If the qth coal powder detection interference coefficient is greater than or equal to the coal powder detection interference threshold, activating the coal powder fineness detection interference correction model; The qth coal powder moisture measurement result and the qth coal powder fineness detection coefficient are input into the coal powder fineness detection interference correction model, and the qth corrected fineness detection coefficient is output.

8. A coal powder fineness detection device based on isokinetic sampling, characterized in that: The device is used to perform a method for detecting coal powder fineness based on isokinetic sampling as described in any one of claims 1 to 7, the device comprising: A conveying scheme obtaining module, used to obtain a coal powder conveying scheme for a coal powder conveying pipeline; A position distribution acquisition module is used to collect the layout parameters of the coal powder sampler of the coal powder conveying pipeline to obtain the initial sampling position distribution; A position distribution adjustment module, for adjusting the initial sampling position distribution according to the coal powder transportation scheme and the coal powder sampling value threshold, to generate an optimized sampling position distribution; an isokinetic sampling module, configured to perform isokinetic sampling on the pulverized coal conveying pipeline according to the optimized sampling position distribution based on the pulverized coal conveying scheme, to obtain Q pulverized coal samples, wherein Q is a positive integer greater than 1; A fineness detection module is used to perform fineness detection on the Q coal powder samples according to the coal powder fineness detection channel to obtain Q coal powder fineness detection coefficients; A sample moisture measurement module is used to measure the moisture of the Q coal powder samples using a coal powder moisture meter to obtain Q coal powder moisture measurement results; The detection report obtaining module is used to perform interference correction on the Q coal powder fineness detection coefficients according to the Q coal powder moisture measurement results to obtain a coal powder fineness detection report.

9. An electronic device, characterized in that: The electronic device comprises: processor; a memory for storing instructions executable by the processor; Wherein, the processor is used to execute a coal powder fineness detection method based on isokinetic sampling as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, so the computer program is used to execute the coal powder fineness detection method based on isokinetic sampling as described in any one of claims 1 to 7.

Images